GraySoft
Projects Models About FAQ Contact Download guIDE →

devworld/gemago-2b-q4_k_m-gguf - Free GGUF Download is indexed on GraySoft with repository links, GGUF quant files, and Hugging Face metadata. This page helps you pick a local model for guIDE or other runtimes. See related models in the same shard below.

Model Intelligence Sheet

devworld/gemago-2b-q4_k_m-gguf overview

This model was converted to GGUF format from DevWorld/Gemago-2b using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

ggufgemmallama-cppgguf-my-repotranslationkoendataset:traintogpb/aihub-koen-translation-integrated-base-10mlicense:apache-2.0license:gemmaendpoints_compatibleregion:us
devworld/gemago-2b-q4_k_m-gguf visual
Downloads
88
Likes
0
Pipeline
translation
Library
Visibility
Public
Access
Open

Repository Files & Downloads

1 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
gemago-2b.Q4_K_M.gguf GGUF Q4_K_M 1.52 GB Download

Model Details Live

Model Slug
devworld/gemago-2b-q4_k_m-gguf
Author
DevWorld
Pipeline Task
translation
Library
Created
2024-05-05
Last Modified
2024-05-20
Gated
No
Private
No
HF SHA
89ab6dd7425ae70be9a52efe8daf9200d5bcb473
License
apache-2.0, gemma
Language
ko, en
Base Model
Unknown

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "language": [
      "ko",
      "en"
    ],
    "license": [
      "apache-2.0",
      "gemma"
    ],
    "tags": [
      "gemma",
      "llama-cpp",
      "gguf-my-repo"
    ],
    "datasets": [
      "traintogpb/aihub-koen-translation-integrated-base-10m"
    ],
    "pipeline_tag": "translation",
    "widget": [
      {
        "text": "Korean:\n나라의 말이 중국과 달라 문자와 서로 통하지 아니하다.\n\nEnglish:\n",
        "example_title": "K2E"
      },
      {
        "text": "English:\nMr. and Mrs. Dursley were proud to say that they were perfectly normal.\n\nKorean:\n",
        "example_title": "E2K"
      }
    ],
    "inference": {
      "parameters": {
        "max_length": 200
      }
    },
    "frontmatter": {
      "language": [
        "ko",
        "en"
      ],
      "license": [
        "apache-2.0",
        "gemma"
      ],
      "tags": [
        "gemma",
        "llama-cpp",
        "gguf-my-repo"
      ],
      "datasets": [
        "traintogpb/aihub-koen-translation-integrated-base-10m"
      ],
      "pipeline_tag": "translation",
      "widget": [
        "text: 'Korean:",
        "text: 'English:"
      ],
      "inference": []
    },
    "hero_image_url": "",
    "summary": "This model was converted to GGUF format from DevWorld/Gemago-2b using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nlanguage:\n- ko\n- en\nlicense:\n- apache-2.0\n- gemma\ntags:\n- gemma\n- llama-cpp\n- gguf-my-repo\ndatasets:\n- traintogpb/aihub-koen-translation-integrated-base-10m\npipeline_tag: translation\nwidget:\n- text: 'Korean:\n\n    나라의 말이 중국과 달라 문자와 서로 통하지 아니하다.\n\n\n    English:\n\n    '\n  example_title: K2E\n- text: 'English:\n\n    Mr. and Mrs. Dursley were proud to say that they were perfectly normal.\n\n\n    Korean:\n\n    '\n  example_title: E2K\ninference:\n  parameters:\n    max_length: 200\n---\n\n# DevWorld/Gemago-2b-Q4_K_M-GGUF\nThis model was converted to GGUF format from [`DevWorld/Gemago-2b`](https://huggingface.co/DevWorld/Gemago-2b) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.\nRefer to the [original model card](https://huggingface.co/DevWorld/Gemago-2b) for more details on the model.\n## Use with llama.cpp\n\nInstall llama.cpp through brew.\n\n```bash\nbrew install ggerganov/ggerganov/llama.cpp\n```\nInvoke the llama.cpp server or the CLI.\n\nCLI:\n\n```bash\nllama-cli --hf-repo DevWorld/Gemago-2b-Q4_K_M-GGUF --model gemago-2b.Q4_K_M.gguf -p \"The meaning to life and the universe is\"\n```\n\nServer:\n\n```bash\nllama-server --hf-repo DevWorld/Gemago-2b-Q4_K_M-GGUF --model gemago-2b.Q4_K_M.gguf -c 2048\n```\n\nNote: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.\n\n```\ngit clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m gemago-2b.Q4_K_M.gguf -n 128\n```\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "gemma",
    "llama-cpp",
    "gguf-my-repo",
    "translation",
    "ko",
    "en",
    "dataset:traintogpb/aihub-koen-translation-integrated-base-10m",
    "license:apache-2.0",
    "license:gemma",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 88,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-20T04:40:17.000Z",
  "created_at": "2024-05-05T13:22:10.000Z",
  "pipeline_tag": "translation",
  "library_name": ""
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "66378802c8950692a44aca99",
  "id": "DevWorld/Gemago-2b-Q4_K_M-GGUF",
  "modelId": "DevWorld/Gemago-2b-Q4_K_M-GGUF",
  "sha": "89ab6dd7425ae70be9a52efe8daf9200d5bcb473",
  "createdAt": "2024-05-05T13:22:10.000Z",
  "lastModified": "2024-05-20T04:40:17.000Z",
  "author": "DevWorld",
  "downloads": 88,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "translation",
  "library_name": "",
  "siblings_count": 4
}